Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 22685
    Prev
    Next
    INDEX
    Explanations

    terms related to the "bottom" or lower positioning in a context, often associated with layout or design elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    bottom

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.63
     виправивши
    -0.58
     متعلقه
    -0.58
     ſind
    -0.56
     
    -0.55
    <?
    -0.54
     Infórmanos
    -0.53
    
    -0.53
    balleur
    -0.53
    UnitTesting
    -0.52
    POSITIVE LOGITS
    bottom
    3.25
     bottom
    2.72
    Bottom
    2.41
     Bottom
    2.38
     BOTTOM
    2.19
    BOTTOM
    2.11
     bottoms
    1.85
    botto
    1.69
    底
    1.53
    底部
    1.41
    Activations Density 0.005%

    No Known Activations